Turkish Captions for Shorts

The Shorts feed is a muted, autoplaying, thumb-driven surface. A Turkish-speaking viewer lands mid-sentence and gives the video about a second. Sound is off by default and often stays off for the whole session, so on-screen text is the primary channel, not a secondary one — the hook has to be readable before it is audible.

YouTube's auto-generated captions for Shorts are a subtitle track: hidden behind a button, rendered in YouTube's style, and unreliable for many languages. Captions burned into the frame are in your font and colour, sit where you put them, and are there whether or not anyone taps CC — and they survive when the clip is downloaded and reposted to Reels or TikTok.

They also carry the middle. Retention on a Short falls off in the first few seconds, and Turkish text moving in time with the speech gives the eye something to track — a reason to stay through the setup and reach the payoff.

One Turkish word can be as long as an English phrase, so Turkish short-form captions are grouped by width rather than by a fixed word count, and the dotless ı and dotted İ are preserved at phone size where a wrong font would merge them.

The transcription is the same one behind the Turkish subtitle generator: the model transcribes the Turkish audio with the correct Turkish letters, resolves the suffix chain on each word using vowel harmony, and splits lines so long agglutinated words stay readable. For Shorts, the result is then split into three- or four-word cards and rendered with a font that has the full Latin with Turkish letters character set, so nothing falls back to a box or a smudge at phone size.